# \#ai-engineer **URL:** https://www.artofsm.art/tag/ai-engineer/421.md [Latest](https://www.artofsm.art/latest.md) · [Categories](https://www.artofsm.art/categories.md) · [Tags](https://www.artofsm.art/tags.md) --- ## [Your Old Prompts Are Making Claude Worse - Lance Martin, Anthropic](https://www.artofsm.art/t/your-old-prompts-are-making-claude-worse-lance-martin-anthropic/27836)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [6 November 2026 21:25 UTC](https://www.artofsm.art/t/your-old-prompts-are-making-claude-worse-lance-martin-anthropic/27836 "2026-11-06T21:25:03Z")
Lance Martin from Anthropic discusses optimizing frontier AI models like Claude 55 by auditing and removing outdated prompt patterns, utilizing prompt caching to reduce costs and latency, and employing well… --- ## [How We Mapped a 35-Million-Line Mainframe in 4 Days - Stephen Chin, Neo4j & Neeraj Deshmukh, Blitzy](https://www.artofsm.art/t/how-we-mapped-a-35-million-line-mainframe-in-4-days-stephen-chin-neo4j-neeraj-deshmukh-blitzy/27834)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [6 November 2026 20:24 UTC](https://www.artofsm.art/t/how-we-mapped-a-35-million-line-mainframe-in-4-days-stephen-chin-neo4j-neeraj-deshmukh-blitzy/27834 "2026-11-06T20:24:48Z")
The presenters describe how combining AI with a knowledge graph enables rapid, accurate modernization of complex legacy mainframe systems by capturing comprehensive code context and dependencies, exemplifie… --- ## [When We Can Do Anything, Do We Still Know What We Want? — Ryo Lu, ex-Cursor | AI Engineer Shanghai](https://www.artofsm.art/t/when-we-can-do-anything-do-we-still-know-what-we-want-ryo-lu-ex-cursor-ai-engineer-shanghai/27803)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [6 November 2026 15:05 UTC](https://www.artofsm.art/t/when-we-can-do-anything-do-we-still-know-what-we-want-ryo-lu-ex-cursor-ai-engineer-shanghai/27803 "2026-11-06T15:05:19Z")
Ryo Lu’s talk explores how powerful AI tools challenge our sense of creativity and identity by making tasks once requiring skill easily replicable, urging us to maintain personal connection and reflection i… --- ## [7 Things Your AI Coworker Needs - Philipp Schmid, Google DeepMind](https://www.artofsm.art/t/7-things-your-ai-coworker-needs-philipp-schmid-google-deepmind/27787)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [6 November 2026 10:23 UTC](https://www.artofsm.art/t/7-things-your-ai-coworker-needs-philipp-schmid-google-deepmind/27787 "2026-11-06T10:23:57Z")
Philipp Schmid from Google DeepMind presents a framework for building autonomous AI co-workers using the Gemini model and managed agents, emphasizing seven essential components—brain, computer, playbooks, t… --- ## [Your AI Isn't the Advantage. Your Judgment Is - Sid Pednekar](https://www.artofsm.art/t/your-ai-isnt-the-advantage-your-judgment-is-sid-pednekar/27784)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [6 November 2026 09:24 UTC](https://www.artofsm.art/t/your-ai-isnt-the-advantage-your-judgment-is-sid-pednekar/27784 "2026-11-06T09:24:22Z")
Dr. Sid Pednekar argues that the true advantage in leveraging AI lies not in the technology itself but in applying human judgment to identify the right problems, foster collaboration, and continuously learn… --- ## [AI Agents Will Upend Investing Even More Than Coding - Frank Long, Coatue](https://www.artofsm.art/t/ai-agents-will-upend-investing-even-more-than-coding-frank-long-coatue/27561)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [6 November 2026 00:23 UTC](https://www.artofsm.art/t/ai-agents-will-upend-investing-even-more-than-coding-frank-long-coatue/27561 "2026-11-06T00:23:50Z")
Frank Long of Coatue explains how AI agents, equipped with comprehensive data access and a combination of deterministic code, machine learning, and human judgment, will revolutionize investing by efficientl… --- ## [Stop Giving Your AI Agents API Keys - Kim Maida, Keycard & Mason Egger, Temporal](https://www.artofsm.art/t/stop-giving-your-ai-agents-api-keys-kim-maida-keycard-mason-egger-temporal/27553)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [5 November 2026 21:25 UTC](https://www.artofsm.art/t/stop-giving-your-ai-agents-api-keys-kim-maida-keycard-mason-egger-temporal/27553 "2026-11-05T21:25:06Z")
Kim Maida and Mason Egger present a secure and reliable framework for AI agents by replacing static API keys with Keycard’s OAuth 2 token exchange for scoped, user-attributed access, combined with Temporal’… --- ## [How Netflix Evaluates AI When There's No Right Answer - Cameron Wolfe, Netflix](https://www.artofsm.art/t/how-netflix-evaluates-ai-when-theres-no-right-answer-cameron-wolfe-netflix/27551)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [5 November 2026 20:25 UTC](https://www.artofsm.art/t/how-netflix-evaluates-ai-when-theres-no-right-answer-cameron-wolfe-netflix/27551 "2026-11-05T20:25:13Z")
Cameron Wolfe from Netflix explains that evaluating AI on subjective tasks requires a multi-step approach combining human evaluation with clear guidelines, automated offline metrics validated against human … --- ## [Why Waiting for the Next AI Model Can Pay Off - John Stecher, Blackstone & Scott Worland, Norm AI](https://www.artofsm.art/t/why-waiting-for-the-next-ai-model-can-pay-off-john-stecher-blackstone-scott-worland-norm-ai/27512)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [5 November 2026 10:25 UTC](https://www.artofsm.art/t/why-waiting-for-the-next-ai-model-can-pay-off-john-stecher-blackstone-scott-worland-norm-ai/27512 "2026-11-05T10:25:24Z")
Scott Worland and John Stecher discuss the importance of robust data strategies, agile prototyping, and rigorous evaluation frameworks in successfully deploying AI models within regulated industries, emphas… --- ## [How We Took an AI Agent From 41% to 97% Accurate - Milind Sunil Shah, Brainbase Labs](https://www.artofsm.art/t/how-we-took-an-ai-agent-from-41-to-97-accurate-milind-sunil-shah-brainbase-labs/27511)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [5 November 2026 09:24 UTC](https://www.artofsm.art/t/how-we-took-an-ai-agent-from-41-to-97-accurate-milind-sunil-shah-brainbase-labs/27511 "2026-11-05T09:24:48Z")
Milind Sunil Shah from Brainbase Labs describes how they developed an AI back-office agent for Domino’s to automate competitor price tracking, improving its accuracy from 41% to 97% through a structured six… --- ## [Stop Making Your Customers Click Approve - Emil Chetty, Wise](https://www.artofsm.art/t/stop-making-your-customers-click-approve-emil-chetty-wise/27507)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [5 November 2026 08:24 UTC](https://www.artofsm.art/t/stop-making-your-customers-click-approve-emil-chetty-wise/27507 "2026-11-05T08:24:22Z")
Emil Chetty from Wise advocates for replacing constant step-by-step user approvals with single, clear job-level agreements that empower AI agents to autonomously execute complex financial tasks within defin… --- ## [Our Smaller Model Beat Opus on Finance Tasks - Alexander Shevchenko, Ramp](https://www.artofsm.art/t/our-smaller-model-beat-opus-on-finance-tasks-alexander-shevchenko-ramp/27497)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [4 November 2026 22:24 UTC](https://www.artofsm.art/t/our-smaller-model-beat-opus-on-finance-tasks-alexander-shevchenko-ramp/27497 "2026-11-04T22:24:44Z")
Alexander Shevchenko from Ramp highlights the company’s applied AI research, including a specialized financial QA model outperforming frontier models, innovative KV cache compression for efficient context s… --- ## [AI Labs Will Trap You or Replace You - Dillon Rolnick, Nous Research](https://www.artofsm.art/t/ai-labs-will-trap-you-or-replace-you-dillon-rolnick-nous-research/27486)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [4 November 2026 21:21 UTC](https://www.artofsm.art/t/ai-labs-will-trap-you-or-replace-you-dillon-rolnick-nous-research/27486 "2026-11-04T21:21:01Z")
Dillon Rolnick emphasizes that as AI becomes widely commercialized, companies must either innovate across different technology layers or develop superior AI agents to solve complex, profitable problems, par… --- ## [Robots Will Be Trained on Video Games - Pim de Witte, General Intuition](https://www.artofsm.art/t/robots-will-be-trained-on-video-games-pim-de-witte-general-intuition/27464)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [4 November 2026 20:24 UTC](https://www.artofsm.art/t/robots-will-be-trained-on-video-games-pim-de-witte-general-intuition/27464 "2026-11-04T20:24:48Z")
Pim de Witte from General Intuition presents a novel method of training robots using vast video game gameplay data, leveraging pixel-to-action models that enable real-time, continuous control across multipl… --- ## [Don't Approve the AI Model. Approve the App - Doneyli De Jesus, Langfuse](https://www.artofsm.art/t/dont-approve-the-ai-model-approve-the-app-doneyli-de-jesus-langfuse/27435)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [4 November 2026 10:24 UTC](https://www.artofsm.art/t/dont-approve-the-ai-model-approve-the-app-doneyli-de-jesus-langfuse/27435 "2026-11-04T10:24:42Z")
Doneyli De Jesus from Langfuse explains that in regulated industries like banking, AI deployment focuses on certifying applications rather than models by using tailored evaluation frameworks with proprietar… --- ## [Why Datasite Stopped Building Its Own Parsing - Adit Abraham, Reducto & Raj Bakhru, Datasite](https://www.artofsm.art/t/why-datasite-stopped-building-its-own-parsing-adit-abraham-reducto-raj-bakhru-datasite/27434)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [4 November 2026 09:24 UTC](https://www.artofsm.art/t/why-datasite-stopped-building-its-own-parsing-adit-abraham-reducto-raj-bakhru-datasite/27434 "2026-11-04T09:24:38Z")
Raj Bakhru of Datasite explains that the company stopped building its own document parsing technology due to the complexity and scale of unstructured financial data, opting instead to partner with Reducto t… --- ## [Building the AI Agent Is Easy. Proving It's Safe Isn't - Jonathan Osborne, NatWest](https://www.artofsm.art/t/building-the-ai-agent-is-easy-proving-its-safe-isnt-jonathan-osborne-natwest/27431)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [4 November 2026 08:25 UTC](https://www.artofsm.art/t/building-the-ai-agent-is-easy-proving-its-safe-isnt-jonathan-osborne-natwest/27431 "2026-11-04T08:25:20Z")
Jonathan Osborne of NatWest explains that while building AI agents like their digital assistant Kora is straightforward, ensuring their safety and reliability in a regulated banking environment is complex d… --- ## [Why AI Makes You 100x Faster but Not Your Company - Mitchell Troyanovsky, Basis](https://www.artofsm.art/t/why-ai-makes-you-100x-faster-but-not-your-company-mitchell-troyanovsky-basis/27420)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [4 November 2026 00:24 UTC](https://www.artofsm.art/t/why-ai-makes-you-100x-faster-but-not-your-company-mitchell-troyanovsky-basis/27420 "2026-11-04T00:24:59Z")
Mitchell Troyanovsky explains that while AI can dramatically boost individual productivity, companies do not see equivalent gains because organizational success depends on consistent, process-driven outcome… --- ## [Without Caching, Your AI Agent Costs 10x More - George Cameron, Artificial Analysis](https://www.artofsm.art/t/without-caching-your-ai-agent-costs-10x-more-george-cameron-artificial-analysis/27403)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [3 November 2026 20:25 UTC](https://www.artofsm.art/t/without-caching-your-ai-agent-costs-10x-more-george-cameron-artificial-analysis/27403 "2026-11-03T20:25:01Z")
George Cameron of Artificial Analysis emphasized the importance of cost optimization in AI deployment, highlighting that caching can reduce agent task expenses by up to ten times and that understanding the … --- ## [Make Your AI Agents Predictable With Graph Engineering - Zachary Blumenfeld, Neo4j](https://www.artofsm.art/t/make-your-ai-agents-predictable-with-graph-engineering-zachary-blumenfeld-neo4j/27371)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [3 November 2026 10:24 UTC](https://www.artofsm.art/t/make-your-ai-agents-predictable-with-graph-engineering-zachary-blumenfeld-neo4j/27371 "2026-11-03T10:24:23Z")
Zachary Blumenfeld presents graph engineering as a method to design AI agent workflows using explicit graphs that enhance predictability, portability, and governance by structuring execution, context, and p… --- ## [Your AI Agents Shouldn't Care Where They Run - Nikhil Harithas, Factory](https://www.artofsm.art/t/your-ai-agents-shouldnt-care-where-they-run-nikhil-harithas-factory/27369)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [3 November 2026 09:24 UTC](https://www.artofsm.art/t/your-ai-agents-shouldnt-care-where-they-run-nikhil-harithas-factory/27369 "2026-11-03T09:24:49Z")
Nikhil Harithas of Factory highlights the challenges of deploying AI agents in secure, complex enterprise environments like Blackstone and presents Factory’s Open Compute as an open-source solution that abs… --- ## [Better Search Took This AI Agent From 36% to 98% Accuracy - Aamir Shakir, Mixedbread](https://www.artofsm.art/t/better-search-took-this-ai-agent-from-36-to-98-accuracy-aamir-shakir-mixedbread/27367)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [3 November 2026 08:25 UTC](https://www.artofsm.art/t/better-search-took-this-ai-agent-from-36-to-98-accuracy-aamir-shakir-mixedbread/27367 "2026-11-03T08:25:03Z")
Mixedbread has developed a privacy-focused, multimodal data retrieval platform that significantly improves AI agent accuracy—from 36% to 98%—by generating multiple embeddings per document to capture detaile… --- ## [You Can't Tell What's Real Anymore. Here's What Comes Next - Cristóbal Valenzuela, Runway](https://www.artofsm.art/t/you-cant-tell-whats-real-anymore-heres-what-comes-next-cristobal-valenzuela-runway/27355)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [3 November 2026 00:25 UTC](https://www.artofsm.art/t/you-cant-tell-whats-real-anymore-heres-what-comes-next-cristobal-valenzuela-runway/27355 "2026-11-03T00:25:10Z")
Cristóbal Valenzuela of Runway discusses the rapid advancement of AI-driven video generation from primitive pixel outputs to hyper-realistic, interactive simulations that learn real-world physics and enable… --- ## [Your Company Should Train Its Own AI Models - Will Brown, Prime Intellect](https://www.artofsm.art/t/your-company-should-train-its-own-ai-models-will-brown-prime-intellect/27342)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [2 November 2026 20:24 UTC](https://www.artofsm.art/t/your-company-should-train-its-own-ai-models-will-brown-prime-intellect/27342 "2026-11-02T20:24:27Z")
Will Brown of Prime Intellect advocates for organizations to train their own AI models using proprietary data to embed institutional knowledge directly into model weights, enabling AI agents to become more … --- ## [A Valid Key Let an AI Agent Delete Production - Sagar Batchu, Speakeasy](https://www.artofsm.art/t/a-valid-key-let-an-ai-agent-delete-production-sagar-batchu-speakeasy/27303)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [2 November 2026 10:24 UTC](https://www.artofsm.art/t/a-valid-key-let-an-ai-agent-delete-production-sagar-batchu-speakeasy/27303 "2026-11-02T10:24:31Z")
Sagar Batchu, CEO of Speakeasy, emphasizes the critical need for robust AI agent governance to prevent costly errors like accidental production deletions by enforcing identity-based policies, real-time deci… --- ## [AI Writes Code Faster Than Your Team Can Review It - Andrew Norrish, Sourcegraph](https://www.artofsm.art/t/ai-writes-code-faster-than-your-team-can-review-it-andrew-norrish-sourcegraph/27300)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [2 November 2026 09:24 UTC](https://www.artofsm.art/t/ai-writes-code-faster-than-your-team-can-review-it-andrew-norrish-sourcegraph/27300 "2026-11-02T09:24:32Z")
Andrew Norrish of Sourcegraph explains that while AI accelerates code generation, it creates a bottleneck in code review and increases incident complexity, placing strain on SREs and platform teams who stru… --- ## [Your AI Pilots Won't Move the P&L. Here's What Will - Adam Nahari, Apollo](https://www.artofsm.art/t/your-ai-pilots-wont-move-the-p-l-heres-what-will-adam-nahari-apollo/27298)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [2 November 2026 08:23 UTC](https://www.artofsm.art/t/your-ai-pilots-wont-move-the-p-l-heres-what-will-adam-nahari-apollo/27298 "2026-11-02T08:23:57Z")
Adam Nahari argues that successful AI transformations require more than deploying technology—they demand strategic change management focused on redesigning workflows, securing executive commitment, and embe… --- ## [I Don't Fear AI Slop. I Fear Untold Stories - Zack Proser, WorkOS](https://www.artofsm.art/t/i-dont-fear-ai-slop-i-fear-untold-stories-zack-proser-workos/27288)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [2 November 2026 00:25 UTC](https://www.artofsm.art/t/i-dont-fear-ai-slop-i-fear-untold-stories-zack-proser-workos/27288 "2026-11-02T00:25:00Z")
Zack Proser highlights the value of creating supportive systems or “factories” that help people efficiently produce meaningful work and share their stories, emphasizing that the real concern is not AI-gener… --- ## [I Made a Fruit Fly Review My Code - Nick Nisi, WorkOS](https://www.artofsm.art/t/i-made-a-fruit-fly-review-my-code-nick-nisi-workos/27281)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [1 November 2026 20:24 UTC](https://www.artofsm.art/t/i-made-a-fruit-fly-review-my-code-nick-nisi-workos/27281 "2026-11-01T20:24:39Z")
Nick Nisi explores using a fruit fly’s neural connectome combined with AI to automate code review, demonstrating that even simple biological networks can accurately identify problematic code, though they la… --- ## [Why We Rebuilt Microsoft Office From Scratch for AI Agents - Yijia Liang, Compound AI](https://www.artofsm.art/t/why-we-rebuilt-microsoft-office-from-scratch-for-ai-agents-yijia-liang-compound-ai/27265)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [1 November 2026 10:24 UTC](https://www.artofsm.art/t/why-we-rebuilt-microsoft-office-from-scratch-for-ai-agents-yijia-liang-compound-ai/27265 "2026-11-01T10:24:17Z")
Yijia Liang explains how Compound AI rebuilt Microsoft Office applications from scratch to create a scalable platform for AI agents tailored to the complex, data-intensive workflows of institutional finance… [Next page](https://www.artofsm.art/tag/ai-engineer/421.md?match_all_tags=true&page=1&tags%5B%5D=ai-engineer)